Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.camel-ai.org/llms.txt

Use this file to discover all available pages before exploring further.

​
WorkflowSelectionMethod

class WorkflowSelectionMethod(Enum):
Enum representing the method used to select workflows. Parameters:
  • AGENT_SELECTED: Agent-based intelligent selection using metadata.
  • ROLE_NAME_MATCH: Pattern matching by role_name.
  • MOST_RECENT: Fallback to most recent workflows.
  • ALL_AVAILABLE: Returned all workflows (fewer than max requested).
  • NONE: No workflows available.

​
WorkflowMemoryManager

class WorkflowMemoryManager:
Manages workflow memory operations for workforce workers. This class encapsulates all workflow memory functionality including intelligent loading, saving, and selection of workflows. It separates workflow management concerns from the core worker task processing logic. Parameters:
  • worker (ChatAgent): The worker agent that will use workflows.
  • description (str): Description of the worker’s role.
  • context_utility (Optional[ContextUtility]): Shared context utility for workflow operations. If None, creates a new instance.
  • role_identifier (Optional[str]): Role identifier for organizing workflows by role. If provided, workflows will be stored in role-based folders. If None, uses default workforce context.
  • config (Optional[WorkflowConfig]): Configuration for workflow management. If None, uses default configuration.

​
init

def __init__(
    self,
    worker: ChatAgent,
    description: str,
    context_utility: Optional[ContextUtility] = None,
    role_identifier: Optional[str] = None,
    config: Optional[WorkflowConfig] = None
):

​
_get_context_utility

def _get_context_utility(self):
Get context utility with lazy initialization. Uses role-based context if role_identifier is set, otherwise falls back to default workforce shared context.

​
_extract_existing_workflow_metadata

def _extract_existing_workflow_metadata(self, file_path: Path):
Extract metadata from an existing workflow file for versioning. This method reads the metadata section from an existing workflow markdown file to retrieve version number and creation timestamp, enabling proper version tracking when updating workflows. Parameters:
  • file_path (Path): Path to the existing workflow file.
Returns: Optional[WorkflowMetadata]: WorkflowMetadata instance if file exists and metadata is successfully parsed, None otherwise.

​
_try_role_based_loading

def _try_role_based_loading(
    self,
    role_name: str,
    pattern: Optional[str],
    max_files_to_load: int,
    use_smart_selection: bool
):
Try loading workflows from role-based directory structure. Parameters:
  • role_name (str): Role name to load workflows from.
  • pattern (Optional[str]): Custom search pattern for workflow files.
  • max_files_to_load (int): Maximum number of workflow files to load.
  • use_smart_selection (bool): Whether to use agent-based selection.
Returns: bool: True if workflows were successfully loaded, False otherwise.

​
_try_session_based_loading

def _try_session_based_loading(
    self,
    session_id: str,
    role_name: str,
    pattern: Optional[str],
    max_files_to_load: int,
    use_smart_selection: bool
):
Try loading workflows from session-based directory (deprecated). Parameters:
  • session_id (str): Workforce session ID to load from.
  • role_name (str): Role name (for deprecation warning).
  • pattern (Optional[str]): Custom search pattern for workflow files.
  • max_files_to_load (int): Maximum number of workflow files to load.
  • use_smart_selection (bool): Whether to use agent-based selection.
Returns: bool: True if workflows were successfully loaded, False otherwise.

​
_session_based_smart_loading

def _session_based_smart_loading(self, session_id: str, max_files_to_load: int):
Load workflows from session using smart selection. Parameters:
  • session_id (str): Session ID to load from.
  • max_files_to_load (int): Maximum number of files to load.
Returns: bool: True if workflows were loaded, False otherwise.

​
_session_based_pattern_loading

def _session_based_pattern_loading(
    self,
    pattern: Optional[str],
    session_id: str,
    max_files_to_load: int
):
Load workflows from session using pattern matching. Parameters:
  • pattern (Optional[str]): Pattern for file matching.
  • session_id (str): Session ID to load from.
  • max_files_to_load (int): Maximum number of files to load.
Returns: bool: True if workflows were loaded, False otherwise.

​
load_workflows

def load_workflows(
    self,
    pattern: Optional[str] = None,
    max_files_to_load: Optional[int] = None,
    session_id: Optional[str] = None,
    use_smart_selection: bool = True
):
Load workflow memories using intelligent agent-based selection. This method first tries to load workflows from the role-based folder structure. If no workflows are found and session_id is provided, falls back to session-based loading (deprecated). Parameters:
  • pattern (Optional[str]): Legacy parameter for backward compatibility. When use_smart_selection=False, uses this pattern for file matching. Ignored when smart selection is enabled.
  • max_files_to_load (Optional[int]): Maximum number of workflow files to load. If None, uses config.default_max_files_to_load. (default: :obj:None)
  • session_id (Optional[str]): Deprecated. Specific workforce session ID to load from using legacy session-based organization. (default: :obj:None)
  • use_smart_selection (bool): Whether to use agent-based intelligent workflow selection. When True, uses workflow information and LLM to select most relevant workflows. When False, falls back to pattern matching. (default: :obj:True)
Returns: bool: True if workflow memories were successfully loaded, False otherwise. Check logs for detailed error messages.

​
load_workflows_by_role

def load_workflows_by_role(
    self,
    role_name: Optional[str] = None,
    pattern: Optional[str] = None,
    max_files_to_load: Optional[int] = None,
    use_smart_selection: bool = True
):
Load workflow memories from role-based directory structure. This method loads workflows from the new role-based folder structure: workforce_workflows/{role_name}/*.md Parameters:
  • role_name (Optional[str]): Role name to load workflows from. If None, uses the worker’s role_name or role_identifier.
  • pattern (Optional[str]): Custom search pattern for workflow files. Ignored when use_smart_selection=True.
  • max_files_to_load (Optional[int]): Maximum number of workflow files to load. If None, uses config.default_max_files_to_load. (default: :obj:None)
  • use_smart_selection (bool): Whether to use agent-based intelligent workflow selection. When True, uses workflow information and LLM to select most relevant workflows. When False, falls back to pattern matching. (default: :obj:True)
Returns: bool: True if workflow memories were successfully loaded, False otherwise.

​
save_workflow

def save_workflow(self, conversation_accumulator: Optional[ChatAgent] = None):
Save the worker’s current workflow memories using agent summarization. This method uses a two-pass approach: first generates the workflow summary to determine operation_mode (update vs create), then saves to the appropriate file path based on that decision. Parameters:
  • conversation_accumulator (Optional[ChatAgent]): Optional accumulator agent with collected conversations. If provided, uses this instead of the main worker agent.
Returns: Dict[str, Any]: Result dictionary with keys:
  • status (str): “success” or “error”
  • summary (str): Generated workflow summary
  • file_path (str): Path to saved file
  • worker_description (str): Worker description used

​
generate_workflow_summary

def generate_workflow_summary(self, conversation_accumulator: Optional[ChatAgent] = None):
Generate a workflow summary without saving to disk. This method generates a workflow summary by calling a dedicated summarizer agent. It does NOT save to disk - only generates the summary content and structured output. Use this when you need to inspect the summary (e.g., extract operation_mode) before determining where to save it. Parameters:
  • conversation_accumulator (Optional[ChatAgent]): Optional accumulator agent with collected conversations. If provided, uses this instead of the main worker agent.
Returns: Dict[str, Any]: Result dictionary with:
  • structured_summary: WorkflowSummary instance or None
  • summary_content: Raw text content
  • status: “success” or error message

​
save_workflow_content

def save_workflow_content(
    self,
    workflow_summary: 'WorkflowSummary',
    context_utility: Optional[ContextUtility] = None,
    conversation_accumulator: Optional[ChatAgent] = None
):
Save a pre-generated workflow summary to disk. This method takes a pre-generated WorkflowSummary object and saves it to disk using the provided context utility. It does NOT call the LLM - just formats and saves the content. Use this for two-pass workflows where the summary is generated first, then saved to a location determined by the summary content. Parameters:
  • workflow_summary (WorkflowSummary): Pre-generated workflow summary object containing task_title, agent_title, etc.
  • context_utility (Optional[ContextUtility]): Context utility with correct working directory. If None, uses default.
  • conversation_accumulator (Optional[ChatAgent]): An optional agent that holds accumulated conversation history. Used to get accurate message_count metadata. (default: :obj:None)
Returns: Dict[str, Any]: Result dictionary with keys:
  • status (str): “success” or “error”
  • summary (str): Formatted workflow summary
  • file_path (str): Path to saved file
  • worker_description (str): Worker description used

​
_select_relevant_workflows

def _select_relevant_workflows(
    self,
    workflows_metadata: List[Dict[str, Any]],
    max_files: int,
    session_id: Optional[str] = None
):
Use worker agent to select most relevant workflows. This method creates a prompt with all available workflow information and uses the worker agent to intelligently select the most relevant workflows based on the worker’s role and description. Parameters:
  • workflows_metadata (List[Dict[str, Any]]): List of workflow information dicts (contains title, description, tags, file_path).
  • max_files (int): Maximum number of workflows to select.
  • session_id (Optional[str]): Specific workforce session ID to search in for fallback pattern matching. If None, searches across all sessions. (default: :obj:None)
Returns: tuple[List[str], WorkflowSelectionMethod]: Tuple of (selected workflow file paths, selection method used).

​
_format_workflows_for_selection

def _format_workflows_for_selection(self, workflows_metadata: List[Dict[str, Any]]):
Format workflow information into a readable prompt for selection. Parameters:
  • workflows_metadata (List[Dict[str, Any]]): List of workflow information dicts (contains title, description, tags, file_path).
Returns: str: Formatted string presenting workflows for LLM selection.

​
_find_workflow_files

def _find_workflow_files(self, pattern: Optional[str], session_id: Optional[str] = None):
Find and return sorted workflow files matching the pattern. .. note:: Session-based workflow search will be deprecated in a future version. Consider using :meth:_find_workflow_files_by_role for role-based organization instead. Parameters:
  • pattern (Optional[str]): Custom search pattern for workflow files. If None, uses worker role_name to generate pattern.
  • session_id (Optional[str]): Specific session ID to search in. If None, searches across all sessions.
Returns: List[str]: Sorted list of workflow file paths (empty if validation fails).

​
_find_workflow_files_by_role

def _find_workflow_files_by_role(
    self,
    role_name: Optional[str] = None,
    pattern: Optional[str] = None
):
Find workflow files in role-based directory structure. This method searches for workflows in the new role-based folder structure: workforce_workflows/{role_name}/*.md Parameters:
  • role_name (Optional[str]): Role name to search for. If None, uses the worker’s role_name or role_identifier.
  • pattern (Optional[str]): Custom search pattern for workflow files. If None, searches for all workflow files in the role directory.
Returns: List[str]: Sorted list of workflow file paths by modification time (most recent first).

​
_collect_workflow_contents

def _collect_workflow_contents(self, workflow_files: List[str]):
Collect and load workflow file contents. Also populates the _loaded_workflow_paths mapping for use during workflow save operations (to support update mode). Parameters:
  • workflow_files (List[str]): List of workflow file paths to load.
Returns: List[Dict[str, str]]: List of dicts with ‘filename’ and ‘content’ keys.

​
_format_workflow_list

def _format_workflow_list(self, workflows_to_load: List[Dict[str, str]]):
Format a list of workflows into a readable string. This is a helper method that formats workflow content without adding outer headers/footers. Used by _format_workflows_for_context and _prepare_workflow_prompt. Parameters:
  • workflows_to_load (List[Dict[str, str]]): List of workflow dicts with ‘filename’ and ‘content’ keys.
Returns: str: Formatted workflow list string.

​
_format_workflows_for_context

def _format_workflows_for_context(self, workflows_to_load: List[Dict[str, str]]):
Format workflows into a context string for the agent. Parameters:
  • workflows_to_load (List[Dict[str, str]]): List of workflow dicts with ‘filename’ and ‘content’ keys.
Returns: str: Formatted workflow context string with header and all workflows.

​
_add_workflows_to_system_message

def _add_workflows_to_system_message(self, workflow_context: str):
Add workflow context to agent’s system message. Parameters:
  • workflow_context (str): The formatted workflow context to add.
Returns: bool: True if successful, False otherwise.

​
_load_workflow_files

def _load_workflow_files(self, workflow_files: List[str], max_workflows: int):
Load workflow files and return count of successful loads. Loads all workflows together with a single header to avoid repetition. Clears and repopulates the _loaded_workflow_paths mapping. Parameters:
  • workflow_files (List[str]): List of workflow file paths to load.
  • max_workflows (int): Maximum number of workflows to load.
Returns: int: Number of successfully loaded workflow files.

​
_get_sanitized_role_name

def _get_sanitized_role_name(self):
Returns: str: Sanitized role name suitable for use in filenames.

​
_generate_workflow_filename

def _generate_workflow_filename(self):
Returns: str: Sanitized filename without timestamp and without .md extension. Format: {role_name}{workflow_filename_suffix}

​
_prepare_workflow_prompt

def _prepare_workflow_prompt(self):
Returns: str: Structured prompt for workflow summary.